Search Results for author:
Found 3 papers, 2 papers with code
Internal Activation as the Polar Star for Steering Unsafe LLM Behavior
Large language models (LLMs) have demonstrated exceptional capabilities across a wide range of tasks but also pose significant risks due to their potential to generate harmful content.
EscapeBench: Pushing Language Models to Think Outside the Box
Language model agents excel in long-session planning and reasoning, but existing benchmarks primarily focus on goal-oriented tasks with explicit objectives, neglecting creative adaptation in unfamiliar environments.
Enhancing Dense Retrievers' Robustness with Group-level Reweighting
In this paper, we introduce WebDRO, an efficient approach for clustering the web graph data and optimizing group weights to enhance the robustness of dense retrieval models.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
